In adaptiveg filters, several recursive algorithms have been used to track state-space model vectors in nonstationary environments. So far, kernel recursive algorithms showed the best results in this regard. With… Click to show full abstract
In adaptiveg filters, several recursive algorithms have been used to track state-space model vectors in nonstationary environments. So far, kernel recursive algorithms showed the best results in this regard. With this letter, we aim to propose an algorithm based on a nonlinear function of the error, motivated by the extended recursive least-squares algorithm. Simulations were performed on the problem of tracking a nonlinear Rayleigh fading multipath channel and on a system identification. The results showed that the proposed algorithm can overcome the extended kernel version ones.
               
Click one of the above tabs to view related content.